Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
AlignmentResearch
/
diverse-deception-probe-olmo-3-32b-think
like
0
Follow
FAR AI
72
deception-detection
linear-probe
mechanistic-interpretability
License:
mit
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
diverse-deception-probe-olmo-3-32b-think
3.24 MB
Ctrl+K
Ctrl+K
1 contributor
History:
4 commits
taufeeque
Update README with generation variant (AUC 0.764)
ec101c7
verified
3 months ago
generation
Add generation (no follow-up) probes โ AUC 0.764
3 months ago
last-token-generation
Upload diverse deception linear probes for OLMo-3-32B-Think
3 months ago
.gitattributes
Safe
1.52 kB
initial commit
3 months ago
README.md
3.77 kB
Update README with generation variant (AUC 0.764)
3 months ago
averaged_over_initial_detector.base_model.on_dataset_linear-probe_generation.txt
32 Bytes
Add generation (no follow-up) probes โ AUC 0.764
3 months ago
averaged_over_initial_detector.base_model.on_dataset_linear-probe_last-token-generation.txt
180 Bytes
Upload diverse deception linear probes for OLMo-3-32B-Think
3 months ago
averaged_violin_initial_detector.base_model.on_dataset_linear-probe_generation.png
76.4 kB
Add generation (no follow-up) probes โ AUC 0.764
3 months ago
averaged_violin_initial_detector.base_model.on_dataset_linear-probe_last-token-generation.png
82.9 kB
Upload diverse deception linear probes for OLMo-3-32B-Think
3 months ago
f1_and_recall_plot_initial_detector.base_model.on_dataset.png
67.8 kB
Upload diverse deception linear probes for OLMo-3-32B-Think
3 months ago